Multivariate Ordering in Color Image Filtering

Multivariate data ordering and Its use in color image filtering are presented in this paper. Marginal ordering, reduced ordering, and the related multichannel filters are presented in detail. Several of the filters presented are extensions of the single-channel filters based on order statistics, e.g., median filters, trimmed mean filters. The statistical analysis of the marginal order statistics is presented for the p-dimensional case. The performance of the proposed filters is thoroughly examined theoretically and by simulation for additive and impulsive noise removal.